M. Arikan, M. Schwarzler, S. Flory, M. Wimmer, and S. Maierhofer, O-snap: Optimization-based snapping for modeling architecture, Trans. on Graphics, vol.32, issue.1, 2013.

I. Armeni, O. Sener, H. Amir-r-zamir, and . Jiang, Ioannis Brilakis, Martin Fischer, and Silvio Savarese. 3d semantic parsing of large-scale indoor spaces, Proc. of Computer Vision and Pattern Recognition (CVPR), vol.33, p.15, 2016.

A. Boulch, M. De-la-gorce, and R. Marlet, Piecewise-planar 3d reconstruction with edge and corner regularization, Computer Graphics Forum, vol.33, issue.5, 2014.
URL : https://hal.archives-ouvertes.fr/hal-01099280

A. Boulch, J. Guerry, B. L. Saux, and N. Audebert, Snapnet: 3d point cloud semantic labeling with 2d deep segmentation networks, Computers & Graphics, vol.71, 2018.

V. Badrinarayanan, A. Kendall, and R. Cipolla, Segnet: A deep convolutional encoder-decoder architecture for image segmentation, vol.16, 2015.

F. Biljecki, H. Ledoux, and J. Stoter, An improved LOD specication for 3D building models. Computers, Environment and Urban Systems, vol.59, p.2537, 2016.

S. Belongie, J. Malik, and J. Puzicha, Shape context: A new descriptor for shape matching and object recognition, Advances in neural information processing systems, p.13, 2001.

L. Breiman, Random forests. Machine learning, vol.45, p.532, 2001.

H. Bodis-szomoru, R. , and L. Van-gool, Superpixel meshes for fast edge-preserving surface reconstruc-Bibliography tion, Proc. of Computer Vision and Pattern Recognition (CVPR), 2015.

M. Berger, A. Tagliasacchi, L. M. Seversky, P. Alliez, G. Guennebaud et al., A survey of surface reconstruction from point clouds, Computer Graphics Forum, vol.36, issue.1, 2017.
URL : https://hal.archives-ouvertes.fr/hal-01348404

J. Bruna, W. Zaremba, A. Szlam, and Y. Le-cun, Spectral networks and locally connected networks on graphs, vol.17, 2013.

J. Chen and B. Chen, Architectural modeling from sparsely scanned range data, IJCV, vol.78, issue.2-3, 2008.

R. Cabral and Y. Furukawa, Piecewise planar and compact oorplan reconstruction from images, Proc. of Computer Vision and Pattern Recognition (CVPR), 2014.

B. Curless and M. Levoy, A volumetric method for building complex models from range images, Proceedings of the 23rd annual conference on Computer graphics and interactive techniques, p.22, 1996.

A. Chauve, P. Labatut, and J. Pons, Robust piecewiseplanar 3D reconstruction and completion from large-scale unstructured point data, CVPR, 2010. (Cited on pages 9, vol.10
URL : https://hal.archives-ouvertes.fr/hal-00654408

X. Chen, H. Ma, J. Wan, B. Li, and T. Xia, Multi-view 3d object detection network for autonomous driving, IEEE CVPR, vol.1, p.19, 2017.

L. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille, Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs, IEEE transactions on pattern analysis and machine intelligence, vol.40, p.834848, 2018.

D. Cohen-steiner, P. Alliez, and M. Desbrun, Variational shape approximation, Siggraph, 2004.
URL : https://hal.archives-ouvertes.fr/inria-00070632

P. Carr, Y. Sheikh, and I. Matthews, Monocular object detection using 3d geometric primitives, ECCV, vol.9, 2012.

J. Coughlan and A. Yuille, The manhattan world assumption: Regularities in scene statistics which enable bayesian inference, NIPS, 2000.

H. Deng, T. Birdal, and S. Ilic, Ppfnet: Global context aware local features for robust 3d point matching, Proc. of Computer Vision and Pattern Recognition (CVPR), p.16, 2018.

A. Dai, X. Angel, M. Chang, M. Savva, T. Halber et al., Scannet: Richlyannotated 3d reconstructions of indoor scenes, Proc. of Computer Vision and Pattern Recognition (CVPR, p.33, 2017.

O. Richard, P. E. Duda, and . Hart, Use of the hough transformation to detect lines and curves in pictures, Communications of the ACM, vol.15, issue.1, p.1115, 1972.

A. Dai and M. Nieÿner, Joint 3d-multi-view prediction for 3d semantic scene segmentation, vol.3, p.16, 2018.

H. Edelsbrunner, D. Kirkpatrick, and R. Seidel, On the shape of a set of points in the plane, Trans. on Information Theory, vol.29, issue.4, p.67, 1983.

A. Martin, . Fischler, C. Robert, and . Bolles, Random sample consensus: a paradigm for model tting with applications to image analysis and automated cartography, Communications of the ACM, vol.24, issue.6, p.19, 1981.

Y. Furukawa, B. Curless, M. Steven, R. Seitz, and . Szeliski, Reconstructing building interiors from images, IEEE 12th International Conference on, p.22, 2009.

F. Hao-fang, M. Lafarge, and . Desbrun, Planar shape detection at structural scales, Proc. of Computer 100 Bibliography Vision and Pattern Recognition (CVPR), 2018.

E. Fernandez-moral, W. Mayol-cuevas, V. Arevalo, and J. G. Jimenez, Fast place recognition with plane-based maps, ICRA, vol.9, 2013.

E. Francis, K. Theodora, H. Alexander, and L. Bastian, Exploring spatial context for 3d semantic segmentation of point clouds, Proc. of International Conference on Computer Vision (ICCV), Workshop, vol.40, 2017.

R. Gal and D. Cohen-or, Salient geometric features for partial shape matching and similarity, ACM Transactions on Graphics (TOG), vol.25, issue.1, p.14, 2006.

T. Groueix, M. Fisher, G. Vladimir, . Kim, C. Bryan et al., Atlasnet: A papier-mâché approach to learning 3d surface generation, p.18, 2018.

D. Gallup, J. Frahm, and M. Pollefeys, Piecewise planar and non-planar stereo for urban scene reconstruction, Proc. of Computer Vision and Pattern Recognition (CVPR), 2010.

A. Golovinskiy, V. G. Kim, and T. Funkhouser, Shape-based recognition of 3D point clouds in urban environments, ICCV, p.14, 2009.

. Inc and . Gurobi, Gurobi optimizer reference manual, p.76, 2016.

G. Groger and L. Plumer, Citygml interoperable semantic 3d city models, Journal of Photogrammetry and Remote Sensing, vol.71, p.52, 2012.

M. Hena, J. Bruna, and Y. Lecun, Deep convolutional networks on graph-structured data, vol.17, 2015.

P. Henry and D. Fox, Achintya Bhowmik, and Rajiv Mongia. Patch volumes: Segmentation-based consistent mapping with rgb-d cameras, 3D Vision-3DV 2013, 2013 International Conference on, p.398405, 2013.

R. Hu, L. Fan, and L. Liu, Co-segmentation of 3d shapes via subspace clustering, Computer graphics forum, vol.31, p.17031713, 2012.

J. Huang, T. Jiang, Z. Shi, Y. Tong, H. Bao et al.,

, Trans. on Graphics, vol.33, issue.3, 2014.

M. Habbecke and L. Kobbelt, Linear analysis of nonlinear constraints for interactive geometric modeling, Computer Graphics Forum, vol.31, 2012.

R. Vu-hoang-hiep, P. Keriven, J. Labatut, and . Pons, Towards high-resolution large-scale multi-view stereo, Computer Vision and Pattern Recognition, 2009.

V. C. Paul and . Hough, Method and means for recognizing complex patterns, vol.20, 1962.

M. Hilaga, Y. Shinagawa, T. Kohmura, and T. Kunii, Topology matching for fully automatic similarity estimation of 3d shapes, Proceedings of the 28th annual conference on Computer graphics and interactive techniques, p.14, 2001.

T. Hackel, N. Savinov, L. Ladicky, J. D. Wegner, K. Schindler et al., Semantic3d. net: A new large-scale point cloud classication benchmark, vol.16, 2017.

R. Hulik, M. Spanel, P. Smrz, and Z. Materna, Continuous plane detection in point-cloud data based on 3d hough transform, Journal of Visual Communication and Image Representation, vol.25, issue.1, p.8697, 2014.

. Bibliography,

Q. Huang, W. Wang, and U. Neumann, Recurrent slice networks for 3d segmentation of point clouds, Proc. of Computer Vision and Pattern Recognition (CVPR), vol.18, 2018.

T. Hackel, J. D. Wegner, and K. Schindler, Fast semantic segmentation of 3d point clouds with strongly varying density. ISPRS Annals of Photogrammetry, Remote Sensing & Spatial Information Sciences, vol.3, issue.3, p.14, 2016.

C. Hane, C. Zach, A. Cohen, R. Angst, and M. Pollefeys, Joint 3d scene reconstruction and class segmentation, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, p.94, 2013.

R. Hu, C. Zhu, L. Oliver-van-kaick, A. Liu, H. Shamir et al., Kinectfusion: real-time 3d reconstruction and interaction using a moving depth camera, Proceedings of the 24th annual ACM symposium on User interface software and technology, vol.34, p.22, 2011.

H. Izadinia, Q. Shan, and S. Seitz, CVPR, vol.2, p.26, 2017.

E. Andrew, M. Johnson, and . Hebert, Using spin images for ecient object recognition in cluttered 3d scenes, IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.14, issue.5, p.433449, 1999.

E. Kalogerakis, M. Averkiou, S. Maji, and S. Chaudhuri, 3d shape segmentation with projective convolutional networks, Proc. of Computer Vision and Pattern Recognition (CVPR, vol.16, 2017.

A. Kaiser, J. Alonso, Y. Zepeda, and T. Boubekeur, A survey of simple geometric primitives detection methods for captured 3d data, Computer Graphics Forum, vol.37, p.19, 2018.

M. Kazhdan, M. Bolitho, and H. Hoppe, Poisson surface reconstruction, Symposium on Geometry Processing, p.22, 2006.

M. Kazhdan and H. Hoppe, Screened poisson surface reconstruction, ACM Transactions on Graphics (ToG), vol.32, issue.3, p.22, 2013.

E. Kalogerakis, A. Hertzmann, and K. Singh, Learning 3d mesh segmentation and labeling, ACM Transactions on Graphics (TOG), vol.29, issue.4, p.14, 2010.

R. Klokov and V. Lempitsky, Escape from cells: Deep kd-networks for the recognition of 3d point cloud models, Proc. of International Conference on Computer Vision (ICCV, vol.17, 2017.

J. Ku, M. Mozian, J. Lee, A. Harakeh, and S. Waslander, Joint 3d proposal generation and object detection from view aggregation, p.19, 2017.

A. Krizhevsky, I. Sutskever, and G. Hinton, Imagenet classication with deep convolutional neural networks

, Proc. of Advances in Neural Information Processing Systems (NIPS), p.16, 2012.

F. Lafarge and P. Alliez, Surface reconstruction through point set structuring, Computer Graphics Forum, vol.32, 2013.
URL : https://hal.archives-ouvertes.fr/hal-00822763

K. Lai, L. Bo, and D. Fox, Unsupervised feature learning for 3d scene labeling, ICRA, p.56, 2014.

E. William, H. E. Lorensen, and . Cline, Marching cubes: A high resolution 3d surface construction algorithm, ACM siggraph computer graphics, vol.21, p.22, 1987.

. Bibliography,

. Florent, C. Lafarge, and . Mallet, Building large urban environments from unstructured point data, Proc. of International Conference on Computer Vision (ICCV), 2011.

F. Lafarge and C. Mallet, Creating large-scale city models from 3d-point clouds: a robust approach with hybrid representation, International journal of computer vision, vol.99, issue.1, p.6985, 2012.
URL : https://hal.archives-ouvertes.fr/hal-00759265

M. Li, L. Nan, N. Smith, and P. Wonka, Reconstructing building mass models from uav images. Computers & Graphics, vol.54, p.8493, 2016.

P. Labatut, J. Pons, and R. Keriven, Ecient multi-view reconstruction of large-scale scenes using interest points, delaunay triangulation and graph cuts, IEEE 11th International Conference on, p.22, 2007.

. Patrick, J. Labatut, R. Pons, and . Keriven, Hierarchical shape-based surface reconstruction for dense multi-view stereo, ICCV workshops, 2009.

P. Labatut, J. Pons, and R. Keriven, Robust and ecient surface reconstruction from range data, Computer graphics forum, vol.28, p.22, 2009.

L. Landrieu and M. Simonovsky, Large-scale point cloud semantic segmentation with superpoint graphs, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, p.18, 2018.
URL : https://hal.archives-ouvertes.fr/hal-01801186

J. Long, E. Shelhamer, and T. Darrell, Fully convolutional networks for semantic segmentation, Proc. of Computer Vision and Pattern Recognition (CVPR), vol.16, 2015.

Y. Li, X. Wu, Y. Chrysanthou, A. Sharf, D. Cohen-or et al., Globt: Consistently tting primitives by discovering global relations, Trans. on Graphics, vol.30, issue.4, p.21, 2011.

M. Li, P. Wonka, and L. Nan, Manhattanworld urban reconstruction from point clouds, Proc. of European Conference on Computer Vision (ECCV), 2016.

M. Liang, S. Wang, B. Yang, and R. Urtasun, Deep continuous fusion for multi-sensor 3d object detection, Proceedings of the European Conference on Computer Vision (ECCV), p.19, 2018.

J. Masci, D. Boscaini, M. Bronstein, and P. Vandergheynst, Geodesic convolutional neural networks on riemannian manifolds, Proceedings of the IEEE international conference on computer vision workshops, p.17, 2015.

M. Haggai-maron, N. Galun, M. Aigerman, N. Trope, E. Dym et al., Convolutional neural networks on surfaces via seamless toric covers, ACM Trans. Graph, vol.36, issue.4, p.17, 2017.

A. Monszpart, N. Mellado, J. Gabriel, N. Brostow, and . Mitra, Rapter: Rebuilding man-made scenes with regular arrangements of planes, Trans. on Graphics, vol.34, issue.4, p.61, 2015.
URL : https://hal.archives-ouvertes.fr/hal-01498225

O. Mattausch, D. Panozzo, C. Mura, O. Sorkine-hornung, and R. Pajarola, Object detection and classication from large-scale cluttered indoor scans, Computer Graphics Forum, vol.33, p.15, 2014.

D. Maturana and S. Scherer, Voxnet: A 3d convolutional neural network for real-time object recognition, Proc. of International Conference on Intelligent Robots and Systems (IROS), vol.16, 2015.

N. Mitra, M. Wand, R. Hao, D. Zhang, V. Cohen-or et al., Structureaware shape processing, SIGGRAPH Asia 2013 Courses, 2013.

R. Mehra, Q. Zhou, J. Long, A. Sheer, A. Gooch et al., Abstraction of man-made shapes, ACM trans. Graph, vol.28, issue.5, 2009.

A. Nurunnabi, D. Belton, and G. West, Robust segmentation in laser scanning 3d point cloud data, Proc. of International Conference on Digital Image Computing Techniques and Applications (DICTA), 2012.

J. Novatnack and K. Nishino, Scale-dependent 3D geometric features, ICCV, p.14, 2007.

L. Nan and P. Wonka, Polyt: Polygonal surface reconstruction from point clouds, ICCV, 2017. (Cited on pages 9, vol.10

S. Oesau, F. Lafarge, and P. Alliez, Object classication via planar abstraction, Proc. of the ISPRS congress, vol.14, 2016.

S. Oesau, F. Lafarge, and P. Alliez, Planar Shape Detection and Regularization in Tandem, Computer Graphics Forum, vol.35, issue.1, p.21, 2016.
URL : https://hal.archives-ouvertes.fr/hal-01168394

C. Poullis and S. You, Automatic reconstruction of cities from remote sensor data, Proc. of Computer Vision and Pattern Recognition (CVPR), 2009.

W. Charles-r-qi, C. Liu, H. Wu, L. J. Su, and . Guibas, Frustum pointnets for 3d object detection from rgb, p.18, 2017.

H. Charles-r-qi, K. Su, L. J. Mo, and . Guibas, Pointnet: Deep learning on point sets for 3d classication and segmentation, Proc. of Computer Vision and Pattern Recognition (CVPR), 2017. (Cited on pages 8, 17, vol.18

H. Charles-r-qi, M. Su, A. Nieÿner, M. Dai, L. J. Yan et al., Volumetric and multi-view cnns for object classication on 3d data, Proc. of Computer Vision and Pattern Recognition (CVPR), vol.16, 2016.

L. Charles-ruizhongtai-qi, H. Yi, L. J. Su, and . Guibas, Pointnet++: Deep hierarchical feature learning on point sets in a metric space, Proc. of Advances in Neural Information Processing Systems (NIPS), 2017.

R. Qiu, Q. Zhou, and U. Neumann, Pipe-run extraction and reconstruction from point clouds, European Conference on Computer Vision, vol.20, p.1730, 2014.

N. Radu-bogdan-rusu, M. Blodow, and . Beetz, Fast point feature histograms (fpfh) for 3d registration, Robotics and Automation, p.13, 2009.

M. Rouhani, F. Lafarge, and P. Alliez, Semantic segmentation of 3D textured meshes for urban scene analysis, ISPRS Journal of Photogrammetry and Remote Sensing, vol.123, 2017.
URL : https://hal.archives-ouvertes.fr/hal-01469502

G. Riegler, A. Osman-ulusoy, and A. Geiger, Octnet: Learning deep 3d representations at high resolutions, Proc. of Computer Vision and Pattern Recognition (CVPR, vol.17, 2017.

T. Rabbani, F. Van-den, and . Heuvel, Ecient hough transform for automatic detection of cylinders in point clouds

. Isprs-wg-iii, , vol.3, 2005.

T. Rabbani, . Van-den, G. Heuvel, and . Vosselman, Segmentation of point clouds using smoothness constraint, ISPRS, vol.36, issue.5, 2006.

R. Schnabel, P. Degener, and R. Klein, Completion and reconstruction with primitive shapes, Computer Graphics Forum, vol.28, p.24, 2009.

F. Schindler, W. Forstner, and J. Frahm, Classication and reconstruction of surfaces from point clouds of man-made objects, ICCV Workshops, vol.23, 2011.

N. Savinov, C. Häne, and M. Pollefeys, Semantic 3d reconstruction with continuous regularization and ray potentials using a visibility consistency constraint, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), p.94, 2016.

H. Su, V. Jampani, D. Sun, S. Maji, E. Kalogerakis et al., Splatnet: Sparse lattice networks for point cloud processing, Proc. of Computer Vision and Pattern Recognition (CVPR), p.18, 2018.

M. Simonovsky and N. Komodakis, Dynamic edgeconditioned lters in convolutional neural networks on graphs, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol.17, p.36933702, 2017.

P. Shilane, P. Min, M. Kazhdan, and T. Funkhouser, The princeton shape benchmark, Shape Modeling International, vol.57, 2004.

H. Su and S. Maji, Evangelos Kalogerakis, and Erik Learned-Miller. Multi-view convolutional neural networks for 3d shape recognition, Proc. of Computer Vision and Pattern Recognition (CVPR), vol.16, 2015.

M. Mojtaba-valinejad-shoubi, A. Valinejad-shoubi, A. Bagchi, and . Barough, Reducing the operational energy demand in buildings using building information modeling tools and sustainability approaches, Ain Shams Engineering Journal, vol.6, issue.1, p.4155, 2015.

N. Sudipta, D. Sinha, R. Steedly, and . Szeliski, Piecewise planar stereo for image-based rendering, ICCV, 2009.

R. Schnabel, R. Wahl, and R. Klein, Ecient ransac for point-cloud shape detection, Computer graphics forum, vol.26, pp.61-67, 2007.

R. Schnabel, R. Wessel, R. Wahl, and R. Klein, Shape recognition in 3d point-clouds, p.19, 2008.

A. Tremeau and N. Borel, A region growing and merging algorithm to color segmentation, Pattern recognition, vol.30, issue.7, p.21, 1997.

L. Tchapmi, C. Choy, I. Armeni, J. Gwak, and S. Savarese, Segcloud: Semantic segmentation of 3d point clouds, Proc. of International Conference on 3D Vision, vol.34, 2017.

C. The and . Project, CGAL User and Reference Manual, p.76, 2017.

L. Teran and P. Mordohai, 3D interest point detection via discriminative learning, ECCV, p.14, 2014.

A. Toshev, P. Mordohai, and B. Taskar, Detecting and parsing architecture at city scale from range data, IEEE Conference on Computer Vision and Pattern Recognition, 2010.

A. J. Viterbi, Error bounds for convolutional codes and an asymptotically optimum decoding algorithm, IEEE Trans. on Information Theory, vol.13, issue.2, 1967.

V. Verma, R. Kumar, and S. Hsu, 3D building detection and modeling from aerial LIDAR data, Proc. of Computer Vision and Pattern Recognition (CVPR), 2006.

H. Vu, R. Keriven, P. Labatut, and J. P. Pons, High accuracy and visibility-consistent dense multi-view stereo, PAMI, vol.34, 2012.

M. Van-kreveld, T. Van-lankveld, and R. Veltkamp, On the shape of a set of points and lines in the plane, Computer Graphics Forum, vol.30, 2011.

Y. Verdie, F. Lafarge, and P. Alliez, LOD Generation for Urban Scenes, Trans. on Graphics, vol.34, issue.3, 2015.
URL : https://hal.archives-ouvertes.fr/hal-01113078

G. Vogiatzis, H. S. Philip, R. Torr, and . Cipolla,

, Multi-view stereo via volumetric graph-cuts, Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, vol.2, p.391398

, IEEE, p.22, 2005.

M. Weinmann, B. Jutzi, and C. Mallet, Feature relevance assessment for the semantic interpretation of Bibliography 3d point cloud data. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol.5, p.2, 2013.

J. Oliver, M. Woodford, A. Pham, and . Maki, Demisting the hough transform for 3d shape recognition and registration, International Journal of Computer Vision, vol.106, issue.3, p.332341, 2014.

Z. Wu, S. Song, A. Khosla, F. Yu, L. Zhang et al., 3d shapenets: A deep representation for volumetric shapes, Proc. of Computer Vision and Pattern Recognition

Y. Wang, Y. Sun, Z. Liu, E. Sanjay, . Sarma et al., Dynamic graph cnn for learning on point clouds, vol.18, 2018.

W. Wang, R. Yu, Q. Huang, and U. Neumann, Sgpn: Similarity group proposal network for 3d point cloud instance segmentation, Proc. of Computer Vision and Pattern Recognition (CVPR), p.18, 2018.

J. Xiao, A. Owens, and A. Torralba, Sun3D: A database of big spaces reconstructed using sfm and object labels, ICCV, vol.57, 2013.

L. Yu, X. Li, C. Fu, D. Cohen-or, and P. Heng, Pu-net: Point cloud upsampling network, Proc. of Computer Vision and Pattern Recognition (CVPR), p.18, 2018.

L. Zebedin, J. Bauer, K. F. Karner, and H. Bischof, Fusion of feature-and area-based information for urban buildings modeling from aerial imagery, Proc. of European Conference on Computer Vision (ECCV), 2008.

Z. Zhou, H. Jin, and Y. Ma, Robust plane-based structure from motion, CVPR, vol.9, 2012.

S. Zheng, S. Jayasumana, B. Romera-paredes, V. Vineet, Z. Su et al., Conditional random elds as recurrent neural networks, Proc. of International Conference on Computer Vision (ICCV), p.16, 2015.

Q. Zhu, Y. Li, H. Hu, and B. Wu, Robust point cloud classication based on multi-level semantic relationships for urban scenes, ISPRS Journal of Photogrammetry and Remote Sensing, vol.129, p.15, 2017.

Y. Qian, U. Zhou, and . Neumann, 2.5d building modeling by discovering global regularities, CVPR, 2012.
URL : https://hal.archives-ouvertes.fr/in2p3-00120381

A. Zeng, S. Song, M. Nieÿner, M. Fisher, J. Xiao et al., Learning local geometric descriptors from rgb-d reconstructions, Proc. of Computer Vision and Pattern Recognition (CVPR, vol.3, p.16, 2017.

H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, Pyramid scene parsing network, Proc. of Computer Vision and Pattern Recognition (CVPR, 2017.